Skip to content

Commit ed86aac

Browse files
jaiveersinghNVjaiveersinghNV
committed
Isaac ROS 4.0
1 parent 923c0d0 commit ed86aac

File tree

53 files changed

+2801
-295
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

53 files changed

+2801
-295
lines changed

‎README.md‎

Lines changed: 16 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -2,25 +2,26 @@
22

33
NVIDIA-accelerated, deep learned model support for object detection including DetectNet.
44

5-
<div align="center"><img alt="original image" src="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_example.png/" width="300px"/>
6-
<img alt="bounding box predictions using DetectNet" src="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_example_bbox.png/" width="300px"/></div>
5+
<div align="center"><img alt="original image" src="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/release-4.0/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_example.png/" width="300px"/>
6+
<img alt="bounding box predictions using DetectNet" src="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/release-4.0/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_example_bbox.png/" width="300px"/></div>
77

88
## Overview
99

1010
Isaac ROS Object Detection contains ROS 2 packages to perform object
1111
detection.
12-
`isaac_ros_rtdetr`, `isaac_ros_detectnet`, and `isaac_ros_yolov8` each provide a method for spatial
12+
`isaac_ros_rtdetr`, `isaac_ros_detectnet`, `isaac_ros_yolov8`, and `isaac_ros_grounding_dino` each provide a method for spatial
1313
classification using bounding boxes with an input image. Classification
1414
is performed by a GPU-accelerated model of the appropriate architecture:
1515

1616
- `isaac_ros_rtdetr`: [RT-DETR models](https://nvidia-isaac-ros.github.io/concepts/object_detection/rtdetr/index.html)
1717
- `isaac_ros_detectnet`: [DetectNet models](https://nvidia-isaac-ros.github.io/concepts/object_detection/detectnet/index.html)
1818
- `isaac_ros_yolov8`: [YOLOv8 models](https://nvidia-isaac-ros.github.io/concepts/object_detection/yolov8/index.html)
19+
- `isaac_ros_grounding_dino`: [Grounding DINO models](https://nvidia-isaac-ros.github.io/concepts/object_detection/grounding_dino/index.html)
1920

2021
The output prediction can be used by perception functions to
2122
understand the presence and spatial location of an object in an image.
2223

23-
<div align="center"><a class="reference internal image-reference" href="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_nodegraph.png/"><img alt="image" src="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_nodegraph.png/" width="800px"/></a></div>
24+
<div align="center"><a class="reference internal image-reference" href="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/release-4.0/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_nodegraph.png/"><img alt="image" src="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/release-4.0/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_nodegraph.png/" width="800px"/></a></div>
2425

2526
Each Isaac ROS Object Detection package is used in a graph of nodes to provide a
2627
bounding box detection array with object classes from an input image. A
@@ -48,7 +49,7 @@ image, which provides 1K pixels for the person, and fail to detect the
4849
same person in the downscaled resolution, which only provides 0.25K
4950
pixels for the person.
5051

51-
<div align="center"><a class="reference internal image-reference" href="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_example_bboxseg.png/"><img alt="image" src="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_example_bboxseg.png/" width="800px"/></a></div>
52+
<div align="center"><a class="reference internal image-reference" href="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/release-4.0/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_example_bboxseg.png/"><img alt="image" src="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/release-4.0/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_example_bboxseg.png/" width="800px"/></a></div>
5253

5354
Object detection classifies a rectangle of pixels as containing an
5455
object, whereas image segmentation provides more information and uses
@@ -63,10 +64,11 @@ This package is powered by [NVIDIA Isaac Transport for ROS (NITROS)](https://dev
6364

6465
## Performance
6566

66-
| Sample Graph<br/><br/> | Input Size<br/><br/> | AGX Orin<br/><br/> | Orin NX<br/><br/> | Orin Nano Super 8GB<br/><br/> | x86_64 w/ RTX 4090<br/><br/> |
67-
|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|
68-
| [RT-DETR Object Detection Graph](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/benchmarks/isaac_ros_rtdetr_benchmark/scripts/isaac_ros_rtdetr_graph.py)<br/><br/><br/>SyntheticaDETR<br/><br/> | 720p<br/><br/><br/><br/> | [56.5 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_rtdetr_graph-agx_orin.json)<br/><br/><br/>29 ms @ 30Hz<br/><br/> | [33.3 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_rtdetr_graph-orin_nx.json)<br/><br/><br/>40 ms @ 30Hz<br/><br/> | [37.3 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_rtdetr_graph-orin_nano.json)<br/><br/><br/>37 ms @ 30Hz<br/><br/> | [450 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_rtdetr_graph-x86-4090.json)<br/><br/><br/>5.5 ms @ 30Hz<br/><br/> |
69-
| [DetectNet Object Detection Graph](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/benchmarks/isaac_ros_detectnet_benchmark/scripts/isaac_ros_detectnet_graph.py)<br/><br/><br/><br/> | 544p<br/><br/><br/><br/> | [55.4 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_detectnet_graph-agx_orin.json)<br/><br/><br/>37 ms @ 30Hz<br/><br/> | [25.7 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_detectnet_graph-orin_nx.json)<br/><br/><br/>45 ms @ 30Hz<br/><br/> | [33.0 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_detectnet_graph-orin_nano.json)<br/><br/><br/>43 ms @ 30Hz<br/><br/> | [262 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_detectnet_graph-x86-4090.json)<br/><br/><br/>11 ms @ 30Hz<br/><br/> |
67+
| Sample Graph<br/><br/> | Input Size<br/><br/> | AGX Thor<br/><br/> | x86_64 w/ RTX 5090<br/><br/> |
68+
|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
69+
| [DetectNet Object Detection Graph](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/release-4.0/benchmarks/isaac_ros_detectnet_benchmark/scripts/isaac_ros_detectnet_graph.py)<br/><br/> | 544p<br/><br/> | [143 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/release-4.0/results/isaac_ros_detectnet_graph-agx_thor.json)<br/><br/><br/>27 ms @ 30Hz<br/><br/> | [242 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/release-4.0/results/isaac_ros_detectnet_graph-x86-5090.json)<br/><br/><br/>17 ms @ 30Hz<br/><br/> |
70+
| [Grounding DINO Object Detection Graph](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/release-4.0/benchmarks/isaac_ros_grounding_dino_benchmark/scripts/isaac_ros_grounding_dino_graph.py)<br/><br/> | 544p<br/><br/> | [22.9 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/release-4.0/results/isaac_ros_grounding_dino_graph-agx_thor.json)<br/><br/><br/>70 ms @ 30Hz<br/><br/> | [144 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/release-4.0/results/isaac_ros_grounding_dino_graph-x86-5090.json)<br/><br/><br/>15 ms @ 30Hz<br/><br/> |
71+
| [RT-DETR Object Detection Graph](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/release-4.0/benchmarks/isaac_ros_rtdetr_benchmark/scripts/isaac_ros_rtdetr_graph.py)<br/><br/><br/>SyntheticaDETR<br/><br/> | 720p<br/><br/> | [219 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/release-4.0/results/isaac_ros_rtdetr_graph-agx_thor.json)<br/><br/><br/>23 ms @ 30Hz<br/><br/> | [457 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/release-4.0/results/isaac_ros_rtdetr_graph-x86-5090.json)<br/><br/><br/>8.0 ms @ 30Hz<br/><br/> |
7072

7173
---
7274

@@ -84,6 +86,10 @@ Please visit the [Isaac ROS Documentation](https://nvidia-isaac-ros.github.io/re
8486
* [ROS 2 Graph Configuration](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_object_detection/isaac_ros_detectnet/index.html#ros-2-graph-configuration)
8587
* [Troubleshooting](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_object_detection/isaac_ros_detectnet/index.html#troubleshooting)
8688
* [API](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_object_detection/isaac_ros_detectnet/index.html#api)
89+
* [`isaac_ros_grounding_dino`](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_object_detection/isaac_ros_grounding_dino/index.html)
90+
* [Quickstart](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_object_detection/isaac_ros_grounding_dino/index.html#quickstart)
91+
* [Troubleshooting](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_object_detection/isaac_ros_grounding_dino/index.html#troubleshooting)
92+
* [API](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_object_detection/isaac_ros_grounding_dino/index.html#api)
8793
* [`isaac_ros_rtdetr`](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_object_detection/isaac_ros_rtdetr/index.html)
8894
* [Quickstart](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_object_detection/isaac_ros_rtdetr/index.html#quickstart)
8995
* [Try More Examples](https://nvidia-isaac-ros.github.io/repositories_and_packages/isaac_ros_object_detection/isaac_ros_rtdetr/index.html#try-more-examples)
@@ -97,4 +103,4 @@ Please visit the [Isaac ROS Documentation](https://nvidia-isaac-ros.github.io/re
97103

98104
## Latest
99105

100-
Update 2024-12-10: Update to be compatible with JetPack 6.1
106+
Update 2025-10-24: Added Grounding DINO object detection package

‎SECURITY.md‎

Lines changed: 24 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
## Security
2+
3+
NVIDIA is dedicated to the security and trust of our software products and services, including all source code repositories managed through our organization.
4+
5+
If you need to report a security issue, please use the appropriate contact points outlined below. **Please do not report security vulnerabilities through GitHub.**
6+
7+
## Reporting Potential Security Vulnerability in an NVIDIA Product
8+
9+
To report a potential security vulnerability in any NVIDIA product:
10+
- Web: [Security Vulnerability Submission Form](https://www.nvidia.com/object/submit-security-vulnerability.html)
11+
- E-Mail: [email protected]
12+
- We encourage you to use the following PGP key for secure email communication: [NVIDIA public PGP Key for communication](https://www.nvidia.com/en-us/security/pgp-key)
13+
- Please include the following information:
14+
- Product/Driver name and version/branch that contains the vulnerability
15+
- Type of vulnerability (code execution, denial of service, buffer overflow, etc.)
16+
- Instructions to reproduce the vulnerability
17+
- Proof-of-concept or exploit code
18+
- Potential impact of the vulnerability, including how an attacker could exploit the vulnerability
19+
20+
While NVIDIA currently does not have a bug bounty program, we do offer acknowledgement when an externally reported security issue is addressed under our coordinated vulnerability disclosure policy. Please visit our [Product Security Incident Response Team (PSIRT)](https://www.nvidia.com/en-us/security/psirt-policies/) policies page for more information.
21+
22+
## NVIDIA Product Security
23+
24+
For all security-related concerns, please visit NVIDIA's Product Security portal at https://www.nvidia.com/en-us/security

‎gxf_isaac_detectnet/gxf/detectnet/detectnet.cpp‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
// SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
2-
// Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2+
// Copyright (c) 2022-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
33
//
44
// Licensed under the Apache License, Version 2.0 (the "License");
55
// you may not use this file except in compliance with the License.

0 commit comments

Comments
 (0)